Related papers: OSGym: Scalable OS Infra for Computer Use Agents
Modern datacenters schedule heterogeneous workloads across geo-distributed sites with diverse compute capacities, electricity prices, and thermal conditions. Compute utilization, heat generation, cooling demand, and energy consumption are…
With the rapid progress of large language models (LLMs), LLM-powered multi-agent systems (MAS) are drawing increasing interest across academia and industry. However, many current MAS frameworks struggle with reliability and scalability,…
To meet next-generation IoT application demands, edge computing moves processing power and storage closer to the network edge to minimise latency and bandwidth utilisation. Edge computing is becoming popular as a result of these benefits,…
When physical testbeds are out of reach for evaluating a networked system, we frequently turn to simulation. In today's datacenter networks, bottlenecks are rarely at the network protocol level, but instead in end-host software or hardware…
Continual memory augmentation lets computer-using agents (CUAs) learn from prior interactions, but unvetted memories can encode domain-inappropriate or unsafe heuristics--spurious rules that drift from user intent and safety constraints. We…
Large language models (LLMs) and large multimodal models (LMMs) have shown great potential in automating complex tasks like web browsing and gaming. However, their ability to generalize across diverse applications remains limited, hindering…
Autonomous LLM-based agents have emerged as a powerful paradigm for complex task execution, yet the field lacks standardized tools for development, deployment, distribution and discovery of agents. We present Cerebrum, an Agent SDK for AIOS…
We present ContainerGym, a benchmark for reinforcement learning inspired by a real-world industrial resource allocation task. The proposed benchmark encodes a range of challenges commonly encountered in real-world sequential decision making…
Cloud Computing is becoming the leading paradigm for executing scientific and engineering workflows. The large-scale nature of the experiments they model and their variable workloads make clouds the ideal execution environment due to prompt…
Deep video recognition is more computationally expensive than image recognition, especially on large-scale datasets like Kinetics [1]. Therefore, training scalability is essential to handle a large amount of videos. In this paper, we study…
AI-enabled systems are subjected to various types of runtime uncertainties, ranging from dynamic workloads, resource requirements, model drift, etc. These uncertainties have a big impact on the overall Quality of Service (QoS). This is…
Nowadays, in most of the fields, task automation is area of interest and research due to that manual execution of a task is error prone, time consuming, involving more human resources and focus concerning. In the area of Computer laboratory…
Large computer models are ubiquitous in the earth sciences. These models often have tens or hundreds of tuneable parameters and can take thousands of core-hours to run to completion while generating terabytes of output. It is becoming…
With the advent of hundreds of cores on a chip to accelerate applications, the operating system (OS) needs to exploit the existing parallelism provided by the underlying hardware resources to determine the right amount of processes to be…
Manipulating deformable objects has long been a challenge in robotics due to its high dimensional state representation and complex dynamics. Recent success in deep reinforcement learning provides a promising direction for learning to…
Modern power systems face growing risks from cyber-physical attacks, necessitating enhanced resilience due to their societal function as critical infrastructures. The challenge is that defense of large-scale systems-of-systems requires…
GUI agents drive applications through their visual interfaces instead of programmatic APIs, interacting with arbitrary software via taps, swipes, and keystrokes, reaching a long tail of applications that CLI-based agents cannot. Yet…
Operating large-scale scientific facilities requires coordinating diverse subsystems, translating operator intent into precise hardware actions, and maintaining strict safety oversight. Language model-driven agents offer a natural interface…
The rapid advancement of large Vision-Language Models (VLMs) has propelled the development of pure-vision-based GUI Agents, capable of perceiving and operating Graphical User Interfaces (GUI) to autonomously fulfill user instructions.…
Current serverless platforms struggle to optimize resource utilization due to their dynamic and fine-grained nature. Conventional techniques like overcommitment and autoscaling fall short, often sacrificing utilization for practicability or…